TrustBandit: Optimizing Client Selection for Robust Federated Learning Against Poisoning Attacks
Bibliographic record
Abstract
Federated learning enables collaborative model training with privacy preservation. In this framework, individual clients locally train and send updates to a central server for aggregation, making the systems susceptible to poisoning attacks due to the lack of central server visibility. Existing client selection (CS) techniques enhance global accuracy but lack robustness, especially with non-Independently and Identically Distributed (non-IID) data patterns. To address this, our study fortifies CS, emphasizing federated learning's resilience. Specifically, to enhance robustness against poisoning attacks, we integrate a reputation system with Adversarial Multi-Armed Bandit (MAB) algorithms for improved model aggregation. Framing the CS problem as an adversarial MAB problem, our approach effectively estimates each client's reputation, mitigating uncertainties in current reputation values. It establishes a regret bound, showcasing sublinear regret, a desirable characteristic in online learning algorithms. Through experiments on a publicly available dataset, our approach achieves an impressive 94.2% success rate in identifying trustworthy clients.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".